Research Engineer / Scientist, Reinforcement Learning

Highlights

• Own the post-training recipe adapting leading open-weight models for legal work.
• Improve long-horizon legal reasoning and agentic workflows from idea to shipping.
• Design reward functions and verifiers for challenging semi-verifiable legal tasks.

What they offer

• Equity
• Bonus

Ideal candidate

Hands-on research engineer who has owned LLM training runs end-to-end and thrives in small, high-bar teams. Motivated by RL for language models and shipping real capability gains to customers quickly.

Requirements

• Hands-on experience post-training LLMs with SFT and RL including preference optimization
• Direct ownership of training runs and results
• Deep ML fundamentals and reliable distributed training experience
• Strong Python engineering with production-quality code and end-to-end ownership
• Research experience in RL for language models or reward modeling